• Venkata Aditya Tadavarty
• Dr. S. V. G. Reddy
• B. Harsha Raj Reddy
• T. Avinash Reddy

With the advent of the global corona virus pandemic induced by the “novel SARS-CoV-2 (severe acute respiratory syndrome corona virus 2)”, detection of COVID 19 become one of the prime challenges in order to mitigate the adverse effects. Recent studies reveal that a Radiological examination is an effective approach for detecting COVID 19. CT scans of patients can be analyzed using convolution neural network models to discover covid-19. Almost majority of the datasets available today suffer from Class imbalance where the instances of one class are predominant over the other classes. Sufficient sample is required for the model to run. In our proposed system methodology, The Class imbalance problem is identified and addressed in this aspect and their results are compared with the Class Weighted Approach models. Prebuilt CNN Architectures namely, RESNET50 and XCEPTION Models are employed and their accuracies are found to be 85.71 and 74.12 respectively. These models are further employed with Class weighted approach to reduce the class imbalance between COVID and NON-COVID files and their accuracies are increased to 87.06 and 81.67 respectively.

"COVID-19 Detection from CT scans using RESNET50 & XCEPTION CNN Models", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 4, page no.h1-h10, April-2022, Available :http://www.jetir.org/papers/JETIR2204701.pdf

"COVID-19 Detection from CT scans using RESNET50 & XCEPTION CNN Models", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 4, page no. pph1-h10, April-2022, Available at : http://www.jetir.org/papers/JETIR2204701.pdf